1 code implementation • 15 Dec 2023 • Longzhong Lin, Xuewu Lin, Tianwei Lin, Lichao Huang, Rong Xiong, Yue Wang
Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors.
1 code implementation • 20 Nov 2023 • Xuewu Lin, Zixiang Pei, Tianwei Lin, Lichao Huang, Zhizhong Su
We introduce two auxiliary training tasks (Temporal Instance Denoising and Quality Estimation) and propose decoupled attention to make structural improvements, leading to significant enhancements in detection performance.
1 code implementation • 23 May 2023 • Xuewu Lin, Tianwei Lin, Zixiang Pei, Lichao Huang, Zhizhong Su
Firstly, it reduces the computational complexity of temporal fusion from $O(T)$ to $O(1)$, resulting in significant improvements in inference speed and memory usage.
1 code implementation • 19 Nov 2022 • Xuewu Lin, Tianwei Lin, Zixiang Pei, Lichao Huang, Zhizhong Su
Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task.
Ranked #10 on Robust Camera Only 3D Object Detection on nuScenes-C
no code implementations • 23 Mar 2021 • Xuewu Lin, Yu-ang Guo, Jianqiang Wang
Early tracking-by-detection algorithms need to do two feature extractions for detection and tracking.